In our project we4bee, we detected two main air pressure waves in Germany from the Tonga eruption. One from north to south, the second one a few hours later from south to north. We visualized pressure differences for our top bar hive for both waves and interpolated isobares from all locations in Germany.
moreThe proceedings of our Shared Task on Scene Segmentation are now available from ceur-ws: http://ceur-ws.org/Vol-3001
more
Viel zu früh verstarb unser Freund und Kollege Daniel Zoller am 05.10.21 nach schwerer Krankheit.
more
Auf dem gemeinsamen Symposium zum Thema "Mensch - Recht - Digitalisierung" des Oberlandesgericht Bamberg und der Julius-Maximilians-Universität Würzburg in der Neubaukirche hielt heute auch Prof. Dr. Andreas Hotho einen Vortrag mit dem Thema "Künstliche Intelligenz im (Un-)Recht?"
more
In our paper, we introduce a large dataset of in-game item purchase logs from the MOBA game Dota 2 and evaluate the performance of state-of-the-art sequential item recommendation algorithms for helping users to correctly itemize during a game.
more
Our paper "CoBERT: Scientific Collaboration Prediction via Sequential Recommendation" has been accepted at the Second International Workshop on Neural Recommender Systems @ ICDM-21.
moreOur paper “Learning Mathematical Relations Using Deep Tree Models” has been accepted at IEEE ICMLA 2021 special session “Machine Learning for Graphs”.
moreOur workshop paper "Detecting Presence Of Speech In Acoustic Data Obtained From Beehives" got accepted at the DCASE21 (Workshop on Detection and Classification of Acoustic Scenes and Events) and will be presented in November this year
more
We analyze the learned features of models trained with different deep metric learning loss functions on two scales (pixel and image property level) and find that ranking and classification based loss functions tend to differ significantly.
more